The DOI matches its Crossref record; 96 of the 96 references it cites were found in a registry or an index.
RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions
Open accessAbstract
Generative AI models have shown impressive ability to produce images with text prompts, which could benefit creativity in visual art creation and self-expression. However, it is unclear how precisely the generated images express contexts and emotions from the input texts. We explored the emotional expressiveness of AI-generated images and developed RePrompt, an automatic method to refine text prompts toward precise expression of the generated images. Inspired by crowdsourced editing strategies, we curated intuitive text features, such as the number and concreteness of nouns, and trained a proxy model to analyze the feature effects on the AI-generated image. With model explanations of the proxy model, we curated a rubric to adjust text prompts to optimize image generation for precise emotion expression. We conducted simulation and user studies, which showed that RePrompt significantly improves the emotional expressiveness of AI-generated images, especially for negative emotions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This echoes previous research which has demonstrated that sharing stories as well as creating stories can help to co-construct family meaning [44, 116].”
From "When He Feels Cold, He Goes to the Seahorse"—Blending Generative AI into Multimaterial Storymaking for Family Expressive Arts Therapy (2024) · cites this paper as [116]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
Wagner, H. R., Glaser, B. G., & Strauss, A. L. (1968) · Social Forces · doi:10.2307/2575405 · Cited by 46,525
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
LightGBM: A Highly Efficient Gradient Boosting Decision Tree
(2017) · HAL · Cited by 10,512
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01228-7 · Cited by 6,909
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332
Research works printed but not linked: 13
- Barney G. Glaser and Anselm L. Strauss. 2006. The Discovery of grounded theory: strategies for qualitative research. AldineTransaction.
- 10.18653/v1 · DOI
- 10.18653/v1 · DOI
- 10.5555/3295222.3295230 · DOI
- 10.18653/v1 · DOI
- OpenAI. DALL·E 2. Retrieved December 13, 2022 from https://openai.com/dall-e-2
- Jonas Oppenlaender. 2022. Prompt Engineering for Text-Based Generative Art. arXiv 1 1. Retrieved from http://arxiv.org/abs/2204.13988 · arXiv
- 10.18653/v1 · DOI
- 10.18653/v1 · DOI
- 10.18653/v1 · DOI
- R Speer, J Chin, C Havasi - Thirty-First AAAI Conference on Artificial, and Undefined 2017. 2017. Conceptnet 5.5: An open multilingual graph of general knowledge Bachelorthesis. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) ConceptNet, 4444–4451. Retrieved from https://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/viewPaper/14972
- 10.5555/3015812.3015857 · DOI
- 10.18653/v1 · DOI
Cited by
Sorted by citations
PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation
Feng, Y., Wang, X., Wong, K. K., Wang, S., Lu, Y., Zhu, M., Wang, B., & Chen, W. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3327168 · Cited by 124
PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement
Wang, Z., Huang, Y., Song, D., Ma, L., & Zhang, T. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642803 · Cited by 115
PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions
Chung, J. J. Y., & Adar, E. (2023) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3586183.3606777 · Cited by 131
When and How to Use AI in the Design Process? Implications for Human-AI Design Collaboration
Lee, S.-Y., Law, M., & Hoffman, G. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2024.2353451 · Cited by 97
Lee, U., Han, A., Lee, J., Lee, E., Kim, J., Kim, H., & Lim, C. (2024) · Education and Information Technologies · doi:10.1007/s10639-023-12150-4 · Cited by 107
Metadata
- Authors
- Wang, Y., Shen, S., & Lim, B. Y.
- Affiliations
- Agency for Science, Technology and Research (SG)
- National University of Singapore (SG)
- Venue
- Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2023-04-19
- Pages
- 1-29
- OpenAlex
- W4321472415
- Cited by
- 120
- References
- 86
- Citations by year
- 2026: 18 · 2025: 48 · 2024: 46 · 2023: 8
- FWCI
- 35.10
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Ministry of Education, India
- Institute for Health Innovation and Technology, National University of Singapore
- Topics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Life Sciences › Neuroscience › Cognitive Neuroscience › Aesthetic Perception and Analysis
- Keywords
- AI-generated images, emotional expressiveness, text-to-image generation, prompt refinement, negative emotions, proxy models, model explanation, rubrics, visual art creation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
